End of training

README.md

@@ -1,7 +1,7 @@
 
 ---
 license: creativeml-openrail-m
-base_model: runwayml/stable-diffusion-v1-5
+base_model: stabilityai/stable-diffusion-2-1
 instance_prompt: A traffic cone falling on its side on the road
 tags:
 - stable-diffusion
@@ -14,7 +14,7 @@ inference: true
     
 # DreamBooth - Redamancy2299/dreambooth2
 
-This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on A traffic cone falling on its side on the road using [DreamBooth](https://dreambooth.github.io/).
+This is a dreambooth model derived from stabilityai/stable-diffusion-2-1. The weights were trained on A traffic cone falling on its side on the road using [DreamBooth](https://dreambooth.github.io/).
 You can find some example images in the following. 
 
 

checkpoint-1000/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1720686e593df6a7452256ad25bd93095284b55e134f94cb9ffeb9802b3d67
-size 6876576717
+oid sha256:3d8ad143a8517a84700a62e26baa7035bd8bed667905e94a325d0a5a7579d1ba
+size 2415

checkpoint-1000/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0c6b0c1b357c9c653c065ad96e896e6df5ab2acb5eb11c7b231738f67c14b5
-size 21643
+oid sha256:91c31bd947ca572218d63246b0c4b35bf3b55edd361c4f4533b75eef6f28468d
+size 21579

checkpoint-1000/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f810fc7b695697c440d8985f6042b4ba23a9e1027604c265718b518ca29f1b2b
+oid sha256:5df0168a751b1257361283b5aa0c288d7c712011edfd861c618859611a2278ec
 size 559

checkpoint-1000/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75dce924fa558dba337511b449aeddb9046d8b90637b7e719be33485e01aaf03
+oid sha256:e95248609fc637ed08a1d1a53233698e8d0b18b858d65436cf7893787be3fd58
 size 559

checkpoint-1000/unet/config.json

@@ -1,11 +1,16 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -17,7 +22,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -45,7 +50,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "sample_size": 96,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -57,6 +62,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "upcast_attention": true,
+  "use_linear_projection": true
 }

checkpoint-1000/unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d650f67d64142c327886c59ba4b30520a4c06ff554bb75d1494ef9bc0c3e75
-size 3438364325
+oid sha256:5d084337c1357e767608807670329217d8428d9124efab1918d4ddccfb164569
+size 3463923045

checkpoint-500/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f356b6aefcc50a53aaee2aace97b19c6339d5168f3a3951041603ebf222327a
-size 6876576717
+oid sha256:3d8ad143a8517a84700a62e26baa7035bd8bed667905e94a325d0a5a7579d1ba
+size 2415

checkpoint-500/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bf8cb6e19d13056f955b610ee1929e44ed0a4f0c844c11a947d8468927ee5f
-size 21643
+oid sha256:3d0fa737b2da2ec8cc0eaa4a0855b492dd418c38ff5055488b6327c7a189d89e
+size 21579

checkpoint-500/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa4c7be44c959599b8b43bb9bc3371e9e4e5bbc5758b3ab5afcccfda3e72e67
+oid sha256:5df0168a751b1257361283b5aa0c288d7c712011edfd861c618859611a2278ec
 size 559

checkpoint-500/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab55a3894f13a87dca32e5de5f614150f97cf549ab87da046986913765ffabc3
+oid sha256:aac83d063e5e49eecc7301bf55b1703744f97d5fce722fa91c3aa12c444247c3
 size 559

checkpoint-500/unet/config.json

@@ -1,11 +1,16 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -17,7 +22,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -45,7 +50,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "sample_size": 96,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -57,6 +62,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "upcast_attention": true,
+  "use_linear_projection": true
 }

checkpoint-500/unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d2dbd4069ed5d639fe4b3d832b85a35e04ff0f6eafc99beb9472dc4f129a0cd
-size 3438364325
+oid sha256:5d084337c1357e767608807670329217d8428d9124efab1918d4ddccfb164569
+size 3463923045

logs/dreambooth/1688034884.9336262/events.out.tfevents.1688034884.szth-acg-bcc04f1143.szth.baidu.com.21070.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c77aa8bdc225b66891272f3abf0c335506bb6813063908594fd3063aa98c70
+size 2712

logs/dreambooth/1688034884.93538/hparams.yml

@@ -0,0 +1,58 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+adam_weight_decay: 0.01
+allow_tf32: false
+center_crop: false
+checkpointing_steps: 500
+checkpoints_total_limit: null
+class_data_dir: null
+class_labels_conditioning: null
+class_prompt: null
+dataloader_num_workers: 0
+enable_xformers_memory_efficient_attention: false
+gradient_accumulation_steps: 1
+gradient_checkpointing: false
+hub_model_id: null
+hub_token: null
+instance_data_dir: ./zhuitong
+instance_prompt: A traffic cone falling on its side on the road
+learning_rate: 5.0e-06
+local_rank: 0
+logging_dir: logs
+lr_num_cycles: 1
+lr_power: 1.0
+lr_scheduler: constant
+lr_warmup_steps: 0
+max_grad_norm: 1.0
+max_train_steps: 1200
+mixed_precision: null
+num_class_images: 100
+num_train_epochs: 200
+num_validation_images: 4
+offset_noise: false
+output_dir: sd_output/dreambooth2
+pre_compute_text_embeddings: false
+pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
+prior_generation_precision: null
+prior_loss_weight: 1.0
+push_to_hub: true
+report_to: tensorboard
+resolution: 512
+resume_from_checkpoint: null
+revision: null
+sample_batch_size: 4
+scale_lr: false
+seed: null
+set_grads_to_none: false
+skip_save_text_encoder: false
+text_encoder_use_attention_mask: false
+tokenizer_max_length: null
+tokenizer_name: null
+train_batch_size: 1
+train_text_encoder: false
+use_8bit_adam: false
+validation_images: null
+validation_prompt: null
+validation_steps: 100
+with_prior_preservation: false

logs/dreambooth/events.out.tfevents.1688034884.szth-acg-bcc04f1143.szth.baidu.com.21070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe7acd531bfd6ad413386679bd7c0658c0da58eb3eed9078c16474a3336b0c5
+size 100634

model_index.json

@@ -5,14 +5,14 @@
     "transformers",
     "CLIPImageProcessor"
   ],
-  "requires_safety_checker": true,
+  "requires_safety_checker": false,
   "safety_checker": [
-    "stable_diffusion",
-    "StableDiffusionSafetyChecker"
+    null,
+    null
   ],
   "scheduler": [
     "diffusers",
-    "PNDMScheduler"
+    "DDIMScheduler"
   ],
   "text_encoder": [
     "transformers",

scheduler/scheduler_config.json

@@ -1,14 +1,20 @@
 {
-  "_class_name": "PNDMScheduler",
+  "_class_name": "DDIMScheduler",
   "_diffusers_version": "0.18.0.dev0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
   "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
   "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
   "trained_betas": null
 }

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "architectures": [
     "CLIPTextModel"
   ],
@@ -7,18 +7,18 @@
   "bos_token_id": 0,
   "dropout": 0.0,
   "eos_token_id": 2,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 768,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
   "initializer_factor": 1.0,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 77,
   "model_type": "clip_text_model",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
   "pad_token_id": 1,
-  "projection_dim": 768,
+  "projection_dim": 512,
   "torch_dtype": "float16",
   "transformers_version": "4.26.0",
   "vocab_size": 49408

text_encoder/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4311d3fc7b70396637a703ba65b7db30041ba536f569ae8f548312641a0fd6
-size 246187063
+oid sha256:f988248177fc727cf066267b3ccb62e7a74b7e3c5b3efa8a701d563e0f0ea037
+size 680901463

tokenizer/special_tokens_map.json

@@ -13,7 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "!",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer/tokenizer_config.json

@@ -19,7 +19,7 @@
   },
   "errors": "replace",
   "model_max_length": 77,
-  "name_or_path": "/home/fuhongtao/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/aa9ba505e1973ae5cd05f5aedd345178f52f8e6a/tokenizer",
+  "name_or_path": "/home/fuhongtao/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/845609e6cf0a060d8cd837297e5c169df5bff72c/tokenizer",
   "pad_token": "<|endoftext|>",
   "special_tokens_map_file": "./special_tokens_map.json",
   "tokenizer_class": "CLIPTokenizer",

unet/config.json

@@ -1,11 +1,16 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,
-  "attention_head_dim": 8,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
   "block_out_channels": [
     320,
     640,
@@ -17,7 +22,7 @@
   "class_embeddings_concat": false,
   "conv_in_kernel": 3,
   "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
+  "cross_attention_dim": 1024,
   "cross_attention_norm": null,
   "down_block_types": [
     "CrossAttnDownBlock2D",
@@ -45,7 +50,7 @@
   "resnet_out_scale_factor": 1.0,
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
-  "sample_size": 64,
+  "sample_size": 96,
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,
   "time_embedding_dim": null,
@@ -57,6 +62,6 @@
     "CrossAttnUpBlock2D",
     "CrossAttnUpBlock2D"
   ],
-  "upcast_attention": false,
-  "use_linear_projection": false
+  "upcast_attention": true,
+  "use_linear_projection": true
 }

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0775faafd3ee475cdf9fa8621d090bbf50015a3a0d62684a5af6ab041781e5a5
-size 3438364325
+oid sha256:5d084337c1357e767608807670329217d8428d9124efab1918d4ddccfb164569
+size 3463923045

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.18.0.dev0",
-  "_name_or_path": "/home/fuhongtao/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/aa9ba505e1973ae5cd05f5aedd345178f52f8e6a/vae",
+  "_name_or_path": "/home/fuhongtao/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/845609e6cf0a060d8cd837297e5c169df5bff72c/vae",
   "act_fn": "silu",
   "block_out_channels": [
     128,
@@ -20,7 +20,7 @@
   "layers_per_block": 2,
   "norm_num_groups": 32,
   "out_channels": 3,
-  "sample_size": 512,
+  "sample_size": 768,
   "scaling_factor": 0.18215,
   "up_block_types": [
     "UpDecoderBlock2D",

vae/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5cef2a0f410dea412810e1e7dc92b2f6797785c8c0447008ff6e07b99e20f3
+oid sha256:8b7010872555f03f3c7c94b3e510546755d6df0be9f06495b6bb01cc5d368779
 size 334707473